Pets Tseng: raw computed results
The raw ranking from the production similarity calculation (face-embedding centroid cosine → gender-cohort z-normalization). The web-opinion crown, curation, and fusion re-rank are removed.
- 1
96.8%z 6.12 - 2
96.4%z 6.03 - 3
93.7%z 5.54 - 4
91.3%z 5.07 - 5
91.2%z 5.07 - 6
90.9%z 5.01 - 7
89.1%z 4.76 - 8
85.9%z 4.50 - 9
85.6%z 4.48 - 10
85.5%z 4.47 - 11
84.8%z 4.41 - 12
84.6%z 4.40 - 13
84.5%z 4.39 - 14
84.5%z 4.39 - 15
84.5%z 4.38 - 16
84.5%z 4.38 - 17
84.3%z 4.37 - 18
84.1%z 4.36 - 19
83.9%z 4.33 - 20
83.9%z 4.33 - 21
83.8%z 4.32 - 22
82.9%z 4.26 - 23
82.2%z 4.19 - 24
82%z 4.18 - 25
81.9%z 4.17 - 26
81.9%z 4.17 - 27
81.6%z 4.15 - 28
81.6%z 4.15 - 29
81.5%z 4.14 - 30
81%z 4.10 - 31
81%z 4.10 - 32
80.2%z 4.03 - 33
80%z 4.02 - 34
79.6%z 4.01 - 35
74%z 3.95 - 36
73.5%z 3.95 - 37
73%z 3.94 - 38
73%z 3.94 - 39
72.7%z 3.94 - 40
69.6%z 3.90 - 41
69.4%z 3.90 - 42
68.9%z 3.90 - 43
68.3%z 3.89 - 44
66.6%z 3.87 - 45
63.1%z 3.83 - 46
60.3%z 3.80 - 47
59.9%z 3.80 - 48
59.4%z 3.79 - 49
57.1%z 3.77 - 50
57%z 3.76